Open-model cases
GLM-5
Z.ai’s GLM-5 series is a large MoE language-model family for reasoning, coding, and long-horizon agentic work. GLM-5 appeared in February 2026, 5.1 in April, 5.2 in June at 753 billion parameters with a one-million-token context window, and 5.3 in August on the same base with post-training changes; the smaller GLM-5.3-Flash followed days later at 320 billion total and 18 billion active parameters. The larger members’ scale makes self-hosting resource-intensive.
Key terms
- open weights
- MoE
- long context
- agentic engineering
Openness profile
Openness is not uniform across this family. GLM-5.2 publishes its weights under MIT and the implementation repository uses Apache 2.0, while GLM-5.3 ships under a custom licence carrying its own name. Code and model artifacts must still be checked separately, and the complete training dataset is not released.
"Open source", "open model", and "open weights" are not interchangeable. Review code, weights, training information, and license separately for each release.
Connected across the project
Builds on
Related papers
Historical context
Related sections
Primary sources
This is a curated technical map, not a claim of comprehensive coverage.